Prediction of residual stress fields after shot-peening of TRIP780 steel with second-order and artificial neural network models based on multi-impact finite element simulations

Shot-peening is a mechanical surface treatment widely employed to enhance the fatigue life of metallic components by generating compressive residual stress fields below surface. These are mainly impacted selection process parameters. The aim this work propose hybrid approach conduct two predictive models: second-order model and feed-forward artificial neural network model. For purpose, 3D multiple-impact finite element coupled central composite design experiments was employed. A parametric analysis also conducted investigate effect shot diameter, velocity, coverage, impact angle on induced profile within TRIP780 steel. It found that both models predict with good agreement, as function parameters can be used in shot-peening optimization due their responsiveness.